• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.47 no.1
• /
• pp.9-19
• /
• 2024

Deep learning-based computer vision anomaly detection algorithms are widely utilized in various fields. Especially in the manufacturing industry, the difficulty in collecting abnormal data compared to normal data, and the challenge of defining all potential abnormalities in advance, have led to an increasing demand for unsupervised learning methods that rely on normal data. In this study, we conducted a comparative analysis of deep learning-based unsupervised learning algorithms that define and detect abnormalities that can occur when transparent contact lenses are immersed in liquid solution. We validated and applied the unsupervised learning algorithms used in this study to the existing anomaly detection benchmark dataset, MvTecAD. The existing anomaly detection benchmark dataset primarily consists of solid objects, whereas in our study, we compared unsupervised learning-based algorithms in experiments judging the shape and presence of lenses submerged in liquid. Among the algorithms analyzed, EfficientAD showed an AUROC and F1-score of 0.97 in image-level tests. However, the F1-score decreased to 0.18 in pixel-level tests, making it challenging to determine the locations where abnormalities occurred. Despite this, EfficientAD demonstrated excellent performance in image-level tests classifying normal and abnormal instances, suggesting that with the collection and training of large-scale data in real industrial settings, it is expected to exhibit even better performance.

• Journal of Astronomy and Space Sciences
• /
• v.41 no.2
• /
• pp.61-78
• /
• 2024

This study developed a real-time spacecraft pose estimation algorithm that combined a deep learning model and the least-squares method. Pose estimation in space is crucial for automatic rendezvous docking and inter-spacecraft communication. Owing to the difficulty in training deep learning models in space, we showed that actual experimental results could be predicted through software simulations on the ground. We integrated deep learning with nonlinear least squares (NLS) to predict the pose from a single spacecraft image in real time. We constructed a virtual environment capable of mass-producing synthetic images to train a deep learning model. This study proposed a method for training a deep learning model using pure synthetic images. Further, a visual-based real-time estimation system suitable for use in a flight testbed was constructed. Consequently, it was verified that the hardware experimental results could be predicted from software simulations with the same environment and relative distance. This study showed that a deep learning model trained using only synthetic images can be sufficiently applied to real images. Thus, this study proposed a real-time pose estimation software for automatic docking and demonstrated that the method constructed with only synthetic data was applicable in space.

• Journal of the Korean School Mathematics Society
• /
• v.3 no.1
• /
• pp.31-45
• /
• 2000

The idea to be changed first among the general ideas of mathematics is that, from the standpoint of teachers, one-sided teaching is efficient due to the progress of classwork of excessive quantity, and, from the standpoint of students, they say they gave up mathematics publicly feeling uneasiness in every class because of the deficiency of previous learning and interest, and they think all problems are due to the educational system, neglecting their studies, not participating actively in lessons. Therefore this study is, after giving learning points and problem papers of which the degree of difficulty differs to the groups of students divided into the advanced, intermediate, and elementary by personal abilities of learning and concerns, tried out to remove uniformity and integrity of lessons through solving the problems students can, to convert lessons to the learner-oriented that learners take part in voluntarily through discussing, solving the problems, and correcting the errors of them by group-cooperative actions, for the students to realize that they can solve everything only by their own endeavors.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.7
• /
• pp.633-640
• /
• 2001

In this paper we examine the machine learning issues raised by the domain of the Intrusion Detection Systems(IDS), which have difficulty successfully classifying intruders. There systems also require a significant amount of computational overhead making it difficult to create robust real-time IDS. Machine learning techniques can reduce the human effort required to build these systems and can improve their performance. Genetic algorithms are used to improve the performance of search problems, while data mining has been used for data analysis. Data Mining is the exploration and analysis of large quantities of data to discover meaningful patterns and rules. Among the tasks for data mining, we concentrate the classification task. Since classification is the basic element of human way of thinking, it is a well-studied problem in a wide variety of application. In this paper, we propose a classifier system based on genetic algorithm, and the proposed system is evaluated by applying it to IDS problem related to classification task in data mining. We report our experiments in using these method on KDD audit data.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.28B no.12
• /
• pp.27-37
• /
• 1991

In this paper, the novel PLD (Preceding Layer Driven) MLP (Multi Layer Perceptron) neural network model and its learning algorithm is described. This learning algorithm is different from the conventional. This integer weights and hard limit function are used for synaptic weight values and activation function, respectively. The entire learning process is performed by layer-by-layer method. the number of layers can be varied with difficulty of training data. Since the synaptic weight values are integers, the synapse circuit can be easily implemented with CMOS. PLD MLP neural network was applied to English Characters, arbitrary waveform generation and spiral problem.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.05a
• /
• pp.183-186
• /
• 2018

In this paper, we propose the database design for skill learning service through the internet from the viewpoint of service engineering. This paper we describe the outlines for a design theory for skill learning service, which can lead to the satisfaction of both learner and instructor. Compared to other services, motion control learning takes a considerable amount of time, and this leads to a difficulty for learners to rate the quality of the service as well as for the instructors to provide consistent quality and standard of teaching. To solve these problems, we use a relational database with MongoDB which is an unstructured database allowing to flexibly incorporate the demands of both learner and instructor into the database itself.

• Journal of Korea Multimedia Society
• /
• v.22 no.10
• /
• pp.1133-1141
• /
• 2019

Most of the previous studies for bark recognition have focused on the extraction of LBP-like statistical features. Deep learning approach was not well studied because of the difficulty of acquiring large volume of bark image dataset. To overcome the bark dataset problem, this study utilizes the MobileNet which was trained with the ImageNet dataset. This study proposes two approaches. One is to extract features by the pixel-wise convolution and classify the features with SVM. The other is to tune the weights of the MobileNet by flexibly freezing layers. The experimental results with two public bark datasets, BarkTex and Trunk12, show that the proposed methods are effective in bark recognition. Especially the results of the flexible tunning method outperform state-of-the-art methods. In addition, it can be applied to mobile devices because the MobileNet is compact compared to other deep learning models.

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.385-398
• /
• 2021

The complexity of deep learning models affects the real-time performance of gesture recognition, thereby limiting the application of gesture recognition algorithms in actual scenarios. Hence, a residual learning neural network based on a deep convolutional neural network is proposed. First, small convolution kernels are used to extract the local details of gesture images. Subsequently, a shallow residual structure is built to share weights, thereby avoiding gradient disappearance or gradient explosion as the network layer deepens; consequently, the difficulty of model optimisation is simplified. Additional convolutional neural networks are used to accelerate the refinement of deep abstract features based on the spatial importance of the gesture feature distribution. Finally, a fully connected cascade softmax classifier is used to complete the gesture recognition. Compared with the dense connection multiplexing feature information network, the proposed algorithm is optimised in feature multiplexing to avoid performance fluctuations caused by feature redundancy. Experimental results from the ISOGD gesture dataset and Gesture dataset prove that the proposed algorithm affords a fast convergence speed and high accuracy.

• Journal of Information Processing Systems
• /
• v.15 no.5
• /
• pp.1119-1130
• /
• 2019

With the wide spread of Social Network Services (SNS), fake news-which is a way of disguising false information as legitimate media-has become a big social issue. This paper proposes a deep learning architecture for detecting fake news that is written in Korean. Previous works proposed appropriate fake news detection models for English, but Korean has two issues that cannot apply existing models: Korean can be expressed in shorter sentences than English even with the same meaning; therefore, it is difficult to operate a deep neural network because of the feature scarcity for deep learning. Difficulty in semantic analysis due to morpheme ambiguity. We worked to resolve these issues by implementing a system using various convolutional neural network-based deep learning architectures and "Fasttext" which is a word-embedding model learned by syllable unit. After training and testing its implementation, we could achieve meaningful accuracy for classification of the body and context discrepancies, but the accuracy was low for classification of the headline and body discrepancies.

• Nuclear Engineering and Technology
• /
• v.55 no.10
• /
• pp.3515-3524
• /
• 2023

A reinforcement learning framework is proposed for the control problem of outlet steam pressure of the once-through steam generator(OTSG) in this paper. The double-layer controller using Proximal Policy Optimization(PPO) algorithm is applied in the control structure of the OTSG. The PPO algorithm can train the neural networks continuously according to the process of interaction with the environment and then the trained controller can realize better control for the OTSG. Meanwhile, reinforcement learning has the characteristic of difficult application in real-world objects, this paper proposes an innovative pretraining method to solve this problem. The difficulty in the application of reinforcement learning lies in training. The optimal strategy of each step is summed up through trial and error, and the training cost is very high. In this paper, the LSTM model is adopted as the training environment for pretraining, which saves training time and improves efficiency. The experimental results show that this method can realize the self-adjustment of control parameters under various working conditions, and the control effect has the advantages of small overshoot, fast stabilization speed, and strong adaptive ability.